https://github.com/CUAI/CorrectAndSmooth
공식 코드Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
Papers with Code 아카이브
Node Classification on Non-Homophilic (Heterophilic) Graphs
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 15
- 보존된 평가 기록
- 401
There exists a non-trivial set of graphs where graph-aware models underperform their corresponding graph-agnostic models, e.g. SGC and GCN underperform MLP with 1 layer and 2 layers. Although still controversial, people believe the performance degradation results from heterophily, i.e. there exist much more inter-class edges than inner-class edges. This task aims to evaluate models designed for non-homophilic (heterophilic) datasets.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/CUAI/Non-Homophily-Benchmarks
공식 코드https://github.com/GemsLab/H2GCN
공식 코드Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
https://github.com/PetarV-/GAT
공식 코드https://github.com/PwnerHarry/Stronger_GCN
공식 코드Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
https://github.com/SitaoLuan/ACM-GNN
공식 코드https://github.com/Tiiiger/SGC
공식 코드https://github.com/bdy9527/FAGCN
공식 코드Beyond Low-frequency Information in Graph Convolutional Networks
https://github.com/chennnM/GCNII
공식 코드https://github.com/cuai/non-homophily-large-scale
공식 코드Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
https://github.com/divelab/Non-Local-GNN
공식 코드https://github.com/dtortorella/addressing-heterophily-gesn
공식 코드Addressing Heterophily in Node Classification with Graph Echo State Networks
https://github.com/emalgorithm/directed-graph-neural-network
공식 코드Edge Directionality Improves Learning on Heterophilic Graphs
https://github.com/graphdml-uiuc-jlu/geom-gcn
공식 코드https://github.com/ivam-he/BernNet
공식 코드BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
https://github.com/jianhao2016/GPRGNN
공식 코드Adaptive Universal Generalized PageRank Graph Neural Network
https://github.com/klicperajo/ppnp
공식 코드Predict then Propagate: Graph Neural Networks meet Personalized PageRank
https://github.com/mlvlab/DeformableGCN
공식 코드https://github.com/qin87/scalenet
공식 코드https://github.com/recklessronan/glognn
공식 코드Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
https://github.com/samihaija/mixhop
공식 코드MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
https://github.com/smartdata-polito/gcnh
공식 코드GCNH: A Simple Method For Representation Learning On Heterophilous Graphs
https://github.com/susheels/gnns-and-local-assortativity
공식 코드https://github.com/tkipf/pygcn
공식 코드Semi-Supervised Classification with Graph Convolutional Networks
https://github.com/twitter-research/neural-sheaf-diffusion
공식 코드Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
https://github.com/williamleif/GraphSAGE
공식 코드https://github.com/yujun-yan/heterophily_and_oversmoothing
공식 코드Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
https://github.com/yuziGuo/ClenshawGNN
공식 코드https://github.com/yuziGuo/FarOptBasis
공식 코드Graph Neural Networks with Learnable and Optimal Polynomial Bases
https://github.com/1075225782/GCN
Semi-Supervised Classification with Graph Convolutional Networks
https://github.com/2023-MindSpore-1/ms-code-11/tree/main/gcn
Semi-Supervised Classification with Graph Convolutional Networks
https://github.com/30Aniket/Graph-Convolutional-Networks-GCNs
Semi-Supervised Classification with Graph Convolutional Networks
https://github.com/404nofound/gat
https://github.com/4pygmalion/GAT_tensorflow
https://github.com/Anak2016/GAT
https://github.com/AngusMonroe/GAT-pytorch
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.